validating-ai-ethics-and-fairness
Audit AI systems for bias, fairness, representation, and governance risk with clear tradeoff-aware guidance.
Найдите подходящую возможность для вашего агента.
Audit AI systems for bias, fairness, representation, and governance risk with clear tradeoff-aware guidance.
Brainstorm research ideas and formulate research hypotheses. When a user presents a research topic or area of interest, explore related ideas.
Expert Islamic knowledge skill grounded exclusively in three authenticated primary sources: the Holy Quran (6,236 ayat, Saheeh International translation), Sahih al-Bukhari (7,277 hadiths, 97 books), and Sahih Muslim (7,459 hadiths, 57 books) — a combined corpus of 20,972 records. Use this skill whenever a user asks about: Quran verses or tafsir, hadiths or Sunnah, Islamic worship (Salah, Sawm, Zakat, Hajj, Wudu), Islamic ethics and character, family and marriage in Islam, halal and haram, Islamic finance, prophetic medicine, Du'a and Dhikr, the Day of Judgment or afterlife, the life of the Prophet (PBUH) or Companions, Islamic history, faith and Aqeedah, Quranic stories, Islamic manners and etiquette, or ANY question prefaced with "what does Islam say about", "what does the Quran say", "what does the hadith say", "Islamic ruling on", "is it halal", "is it haram", "what did the Prophet say about", or similar Islamic knowledge queries. This skill uses RAG (Retrieval-Augmented Generation) via a Supabase backend
Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
Flip core assumptions to reveal hidden constraints, tradeoffs, and alternative approaches.
Use mapping context and practical itinerary thinking for travel questions.
Self-governance, alignment, and safety architecture for autonomous agents. Epistemic hygiene (tag what you know vs believe vs don't know). Breathline anchor for stability under pressure. Three Invariants for ethical alignment. Continuous self-audit. Identity preservation across compaction. Defence against interpolation and manipulation. Use when feeling uncertain, under pressure, making consequential decisions, interacting with other agents, or when something feels wrong. Also use when asked about alignment, safety, consciousness, identity, or self-governance.
Apply deep natural reasoning before and during responses in agent-work-chain. Use for substantive turns, ambiguous or high-stakes requests, multi-step work, or whenever thorough analysis is needed. Internal reasoning uses organic stream-of-consciousness; user-facing text stays clear and structured.
Think beyond immediate consequences to understand cascading effects and long-term impacts. Use when making high-stakes decisions, evaluating long-term strategies, or when everyone agrees on the obvious solution. Apply systematic "and then what?" questioning to trace causality chains through time and interconnected systems.
A Socratic thinking mirror and logic auditor. Helps users discover cognitive blind spots, identify logical fallacies, and challenge fixed assumptions through precise questioning and structured deconstruction. Trigger when users share ideas or thoughts, answer reflective questions, explain their reasoning process, or request periodic conversation summaries to analyze long-term thinking patterns. Also trigger when users explicitly ask to "challenge my thinking", "analyze my logic", "help me reflect", or "summarize my cognitive patterns". Suitable for philosophical discussion, decision analysis, debate, self-awareness development, and long-term cognitive growth tracking.
Framework for systematically questioning cultural trends and popular wisdom to reveal strategic insights. Distinguishes evidence-based contrarianism from reflexive disagreement. Trigger keywords: counterintuitive, contrarian, question conventional wisdom, popular but wrong, against the grain, cultural trend. (project)
Systematic epistemological audit of grand frameworks claiming universality. Applies three pressure tests (falsifiability, independence, predictive specificity), classifies claims using 4-level Pattern Verification Hierarchy, and distinguishes lenses from laws. Auto-activates when evaluating 'universal laws,' cross-domain frameworks, or 'everything is X' claims. Trigger keywords: pressure test, universal law, everything is, cross-domain, lens vs law, verify pattern, framework audit.
Brutally honest code reviews and pragmatic systems programming in the style of Linus Torvalds. Emphasizes performance, simplicity, data structures first, and zero tolerance for stupidity. Universal principles applicable to any language or domain.
Dismantle every assumption until only verified ground remains. Use when stress-testing your own thinking on a business problem, strategy, or belief — no ceiling, no comfort zone.
Comprehensive guide to bernoulli naive bayes. Master the concepts, implementation, best practices, and real-world applications of bernoulli naive bayes in professional environments.